dsh-o11y-plugin
Unified observability (trace/log/metric) for deepseek-harness plugins: hooks dsh session telemetry where available, maintains OTel signals where not, and exports via standard OTLP.
48 results
Unified observability (trace/log/metric) for deepseek-harness plugins: hooks dsh session telemetry where available, maintains OTel signals where not, and exports via standard OTLP.
DSH web plugin: event-driven skill self-evolution. Watches agent execution traces, crystallizes reusable skills from successful turns via LLM review, progressively improves them, and manages everything in a dedicated Settings section.
BugTraceAI penetration-testing mode for deepseek-harness (dsh): pentester persona, bundled runbook skill, and the BugTraceAI MCP bridge in one installable profile bundle.
Maestro observe — trace/health/cost debug tooling (Phase 3)
vLLM-Ascend Profiler Analyzer — a DeepSeek Harness plugin that ingests vLLM-Ascend / Ascend NPU profiling artifacts, renders a standalone Host+Device swimlane / cost-share / optimization-advice surface, and exports Markdown or PDF reports.
AI deep-reading assistant for DeepSeek Harness and dsh-TUI: extract traceable claims, evidence, confidence levels, knowledge maps, and review questions from articles, books, PDFs, files, URLs, or pasted text.
Local-first code intelligence graph for DeepSeek Harness: structural search, blast radius, temporal memory, and 27 agent skills over Memtrace MCP.
Litefuse observability for DeepSeek Harness: every user turn becomes one agent trace with per-call generations, tool spans, and subagent subtrees
Cross-surface plain-language trajectory visualization and review for DeepSeek Harness.
DeepSeek Harness plugin exposing the CX Agent Studio Scripting API CLI (cxas-scrapi / 'cxas') as model-facing tools: apps, deployments, evaluations, conversations, traces, tools, callbacks, variables, pull/push, and lint.
DSH 插件:把会话轨迹变成可分享、可复盘、可教学的结构化报告(脱敏 + LLM 总结,HTML/MD/JSON 输出)
Session-scoped LLM request and response inspector for DeepSeek Harness Web
AgentTrace 智能体轨迹:DSH 会话日志可视化插件——首页闭环总览 + 三层渐进式查看器(摘要/故事线/事件树)+ 四层进度体系 + 可折叠 JSON 查看器 + SVG 闭环轮环图会话图(每个轮次一个环、子 Agent 分叉环,融合 dsh-seelog)。host 与 client 半均由 tsdown 构建,随 harness 启动。
Stylotrace 深度协作写作 Agent 的 DeepSeek Harness 插件:40 个 MCP 写作工具 + 完整技能包。风格学习(四层向量+外层调制器)、澄清→大纲→逐节写作→红队审计→读者群像,全流程可被 DSH Agent 调用。
Recent conversations stay vivid. Older ones fade into summaries, not oblivion. StrataGate gives DeepSeek Harness six-layer, time-decaying memory, while lasting events and relationships settle into a knowledge graph. Bring your memories from other AIs with
A DeepSeek Harness Web plugin for inspecting redacted LLM HTTP request and response traces.
Native DeepSeek Harness plugin for source-traceable Brave and Tavily web search, with optional TaroCub integration.
轨迹视图插件:在 DeepSeek Harness Web GUI 的「轨迹」标签旁新增可回放的横向时间轴——minimap 总览、搜索、回放、轮次跳转、跟随模式、历史分页、步骤/子调用耗时与吞吐、提示词变更对比、原始请求分析与 Markdown 导出。
Human-and-agent control plane for DeepSeek Harness — visualize live wiring, trace activity, and safely automate plugin blueprints.
Shengyv Writing Architecture 提示词优化:主框 ✨ 一键意图感知改写;C 方案复刻完整会话命中 prompt cache;CAS 写回;trace 落盘;sidebar 事件总线联动
DeepSeek Harness web GUI: collapse the agent trace (tool calls, thinking, workflow steps) while always keeping the agent's final output. A setting controls whether the trace is default-collapsed after the final output completes (default on).
Local-first Skill load evidence, learning cards, and iteration preparation for DeepSeek Harness
Linear algebra toolbox for DeepSeek Harness (dsh): matrix multiply, determinant, inverse, trace, transpose, RREF, linear system solver with unique/infinite/none classification, and vector ops (dot/cross/norm/projection/angle) — zero runtime dependencies
dsh-plugin: quality-first topic memory for dsh — a topic keeps the starting question, conclusion, impact and dependencies, not the process; local-first git-traced OKF bundle, budgeted LLM-free injection